An animated desktop pet plugin for DeepSeek Harness that features physical interactions, real-time API balance tracking, and a full pipeline for creating custom pet characters.

An AI-native quantitative trading platform that automates the pipeline from factor discovery and model training to live trading across global markets.

An AI-powered design review tool for KiCad that analyzes schematics and PCB layouts to catch bugs, simulate circuits via SPICE, and predict EMC risks.

PandaWiki is an AI-powered open-source knowledge base system for building intelligent product and technical documentation with AI-assisted creation, Q&A, and search.

A workflow engine for AI coding agents that uses YAML definitions to make software development processes deterministic, repeatable, and isolated.

Agentic Bug Hunter is an open‑source CLI (and Claude Code plugin) that uses LLMs to automate the full bug‑bounty workflow—recon, vulnerability testing, validation, and report generation—supporting dozens of Web2 and Web3 bug classes and working with free local models (Ollama) or cloud providers.

An agent skill that extracts visual design identities from references into a machine-readable JSON "Design DNA" to ensure faithful and deterministic UI implementation.

A custom ComfyUI node set for Minimax H3 that provides neural latent upscaling and tiled re-sampling to accelerate high-resolution video generation while avoiding VAE round-trip overhead.

A schema-driven CLI for job searching and recruitment that integrates AI-powered resume optimization and MCP support for AI agents.

A visualization intermediate language and compiler that allows AI agents to turn simple chart specifications into polished, professional visualizations across multiple backends like Vega-Lite and Plotly.

A personal AI assistant with a sophisticated eight-type memory system that learns user behavior and operates across multiple apps and devices.

An open-source video localization tool that automates transcription, translation, and dubbing for videos from YouTube, Bilibili, or local files.

A developer SDK providing APIs to build AI agents that can write code, manage files, and execute terminal commands in local or ephemeral workspaces.

A high-performance C++ inference engine for local LLM deployment that supports hybrid MoE offloading across GPU, CPU, NUMA, and disk.

A Python SDK for building stateful AI agents powered by Gemini, providing an infrastructure layer that abstracts the agentic loop and manages tool integration.

DeepAudit is an open‑source, multi‑agent AI security auditor that analyses code, generates and sandbox‑executes PoC exploits, and outputs professional reports. It runs via Docker, supports local LLMs, and aims to reduce false positives and verify vulnerabilities automatically.

A modern open-source Linux server management panel that provides a web GUI for server operations and a unified platform for managing AI models and agents.

An open-source system that compiles raw documents into a structured, interlinked wiki-style knowledge base using LLMs and vectorless, reasoning-based retrieval.

An autonomous, collaborative research pipeline that turns a research idea into a conference-ready academic paper with real citations and sandbox experiments.

An open-source, real-time infrastructure monitoring platform that provides per-second metrics and ML-powered anomaly detection with zero configuration.

An open-source data engineering agent that automates SQL authoring, semantic modeling, and pipeline generation by connecting warehouses, catalogs, and BI tools.

An AI-powered manager for GitHub stars that uses semantic search, AI categorization, and release tracking to turn a pile of starred repositories into a structured library.

A toolkit for the DSH framework that combines a runtime injector, thinking-mode routing presets, and a graded task protocol to prevent model laziness and ensure structured task execution.

A local-first personal AI assistant and readable blueprint for agentic systems, featuring a transparent loop, multi-tiered memory, and built-in LLM-Ops.

PixelRAG renders web pages, PDFs, and images into screenshot tiles, embeds them with a vision‑language model, builds a FAISS/Qdrant vector index, and provides a searchable API (or Claude plugin) so LLMs can retrieve information based on visual layout rather than plain text.

A native desktop GUI for the Hermes Agent, simplifying the installation, configuration, and management of a self-improving AI assistant with tool use and messaging integrations.

An enterprise-grade, self-hosted AgentOS that uses domain ontologies to govern AI agent reasoning and execution for trustworthy, tool-augmented task completion.

An information processor for quantitative finance that transforms raw papers and news into structured, cited, and timestamped financial knowledge for RAG and agentic reasoning.

A file-backed, spec-driven workflow framework that gives AI coding agents a structured process for planning, building, and verifying software features one at a time.

A methodology and CLI tool that transforms AI coding prompts into structured design contracts using the REASONS Canvas framework to ensure precise, traceable code generation.

A reproducible post-training and evaluation pipeline for long-horizon shopping agents using LoRA SFT and GRPO to optimize tool use and constraint satisfaction in the ShopSimulator environment.

An open platform of omnimodal world models and tools for building Physical AI, enabling the joint processing and generation of text, vision, audio, and action sequences for robotics and autonomous systems.

Magic Context is a CortexKit plugin that gives coding‑assistant agents a self‑managing long‑term memory. It captures useful facts from chat history, consolidates them in the background, and automatically recalls relevant memories across sessions, eliminating the disruptive compaction pauses typical of AI‑coding tools.

A collection of open-source inference technologies from Perplexity AI, featuring RDMA-based communication for LLMs, a CPU-optimized tokenizer, and a Metal-based inference server for Apple Silicon.

A walkable 3D video store interface for media libraries like Jellyfin, Plex, and Emby that turns digital catalogs into an immersive physical browsing experience.

A cross-platform machine learning accelerator that optimizes inference and training for models from various frameworks like PyTorch and TensorFlow.

A framework that bundles LLMs and speech-to-text tools into single-file executables for zero-installation, cross-platform local execution.

An AI-powered penetration testing agent that automates the full cycle of reconnaissance, vulnerability discovery, and exploitation via natural language commands.

EchoBird is a cross‑platform desktop app (Tauri + Rust) that lets you install, launch, and manage a wide range of AI coding assistants, chat agents and local LLM runtimes from a single UI. Its core feature – the **Model Nexus** – stores provider credentials once and automatically rewrites each tool’s native config, so you can switch models everywhere with one click.

A privacy-focused desktop AI companion that can operate your computer, manage files, and use MCP tools, featuring a hormone-based emotion system and a Live2D avatar.

An AI-native terminal and infrastructure agent that allows engineers to manage cloud resources and servers using natural language instead of complex commands.

Semble is a CPU‑only Python library/CLI/MCP server that indexes a codebase in ~0.5 s and answers natural‑language code queries in ~1 ms, delivering transformer‑level relevance while using ~99 % fewer tokens than a grep‑plus‑read baseline. It combines static code embeddings (Model2Vec) with BM25, fuses results, and applies code‑aware reranking. Integrates with Claude Code, Codex, Cursor, OpenCode, etc., and requires no API keys or GPUs.

An AI-powered UI design and reconstruction tool that generates high-fidelity UI mockups and converts them into functional HTML/CSS or WeChat Mini Program code.

A real-time monitoring dashboard for NVIDIA DGX Spark and NVIDIA GPU Linux hosts that tracks hardware metrics and LLM inference performance.

An open-source desktop workbench for the local Grok Build CLI that provides a visual interface for managing AI agent sessions, code editing, and remote IM connectivity.

A production-ready orchestration layer for running high-performance LLMs on-device across mobile, web, and IoT platforms using LiteRT.

A production-ready Java framework for building agentic, workflow-based, and multi-agent applications with built-in support for state management and context engineering.

A reference stack for running AI agents safely within NVIDIA OpenShell sandboxes, providing managed inference, network policies, and lifecycle operations.